Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Structuring the skies: Diel dynamics of migratory animal movement in the lower atmosphere.

Ecology·2025
Same author

Fair human-centric image dataset for ethical AI benchmarking.

Nature·2025
Same author

Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations.

Proceedings. International Conference on 3D Vision·2024
Same author

The Curious Layperson: Fine-Grained Image Recognition Without Expert Labels.

International journal of computer vision·2024
Same author

Quantifying long-term phenological patterns of aerial insectivores roosting in the Great Lakes region using weather surveillance radar.

Global change biology·2022
Same author

AutoNovel: Automatically Discovering and Learning Novel Visual Categories.

IEEE transactions on pattern analysis and machine intelligence·2021
Same journal

A Guide to Structureless Visual Localization.

International journal of computer vision·2026
Same journal

Distillation-free Scaling of Large State-Space Models for Images and Videos.

International journal of computer vision·2026
Same journal

Are Minimal Radial Distortion Solvers Really Necessary for Relative Pose Estimation?

International journal of computer vision·2026
Same journal

Structure-from-motion in micro-image domain for uncalibrated plenoptic 2.0 cameras.

International journal of computer vision·2026
Same journal

FourierMIL: Fourier Filtering-based Multiple Instance Learning for Whole Slide Image Analysis.

International journal of computer vision·2025
Same journal

A Likelihood Ratio-Based Approach to Segmenting Unknown Objects.

International journal of computer vision·2025
See all related articles

Related Experiment Video

Updated: Mar 17, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K

Deep Filter Banks for Texture Recognition, Description, and Segmentation.

Mircea Cimpoi1, Subhransu Maji2, Iasonas Kokkinos3

  • 1University of Oxford, Oxford, UK.

International Journal of Computer Vision
|July 30, 2016
PubMed
Summary
This summary is machine-generated.

This study introduces a human-interpretable vocabulary for texture attributes and new datasets for benchmarking. It demonstrates efficient deep learning methods for texture recognition, achieving state-of-the-art results.

Keywords:
Convolutional neural networksDatasets and benchmarksFilter banksFisher vectorsTexture and material recognitionVisual attributes

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

11.1K
Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

257

Related Experiment Videos

Last Updated: Mar 17, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

11.1K
Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

257

Area of Science:

  • Computer Vision
  • Machine Learning
  • Image Analysis

Background:

  • Visual textures are crucial for image semantics and have driven advancements in image understanding.
  • Traditional texture representations, like bag-of-visual-words and Fisher vectors, have been impactful but require adaptation for modern deep learning.

Purpose of the Study:

  • To develop a human-interpretable vocabulary for texture attributes and create a benchmark dataset.
  • To address texture and material recognition under realistic, cluttered conditions.
  • To enhance classic texture representations using deep learning for improved efficiency and generalization.

Main Methods:

  • Proposed a novel vocabulary of texture attributes and a corresponding describable texture dataset.
  • Developed benchmarks for material and texture attribute recognition on the OpenSurfaces dataset, focusing on cluttered scenes.
  • Revisited bag-of-visual-words and Fisher vectors by utilizing convolutional layers of deep models as filter banks.

Main Results:

  • Achieved state-of-the-art performance across multiple datasets, extending beyond texture recognition tasks.
  • Demonstrated the efficiency and generalization capabilities of deep learning-enhanced classic texture representations.
  • Showcased benefits in feature transfer across different domains and efficient application of deep features to image regions.

Conclusions:

  • The proposed texture attribute vocabulary and datasets advance texture understanding and benchmarking.
  • Integrating deep learning with classic texture representations offers an efficient and effective approach for image analysis.
  • The methods provide robust performance in realistic conditions and facilitate domain transfer.